Predicting axial capacity of driven piles in cohesive soils using intelligent computing

摘要: An accurate prediction of pile capacity under axial loads is necessary for the design. This paper presents development a new model to predict foundations driven into cohesive soils. Gene expression programming technique (GEP) has been utilized this purpose. The data used GEP collected from literature and comprise series in-situ piles load tests as well cone penetration test (CPT) results. are divided two subsets: training set calibration independent validation verification. Predictions compared with experimental predictions number currently adopted CPT-based methods. results have demonstrated that performs coefficient correlation, mean probability density at 50% equivalent 0.94, 0.96 1.01, respectively, indicating proposed predicts accurately.